Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 11934
    Prev
    Next
    INDEX
    Explanations

    terms related to theoretical concepts in mathematics or physics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    meaning "again" in different languages

    np_acts-logits-general · gemini-2.0-flash

    again

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ^(@)
    -0.68
    onViewCreated
    -0.62
    Espèce
    -0.61
    hassee
    -0.59
     "..\..\
    -0.59
    */].
    -0.59
     censiti
    -0.58
    findpost
    -0.58
    ^(@
    -0.58
    UnsafeEnabled
    -0.58
    POSITIVE LOGITS
     again
    3.21
    Again
    2.88
    again
    2.88
     Again
    2.80
     AGAIN
    2.42
     novamente
    2.39
     nuevamente
    2.25
     опять
    2.13
     opět
    2.07
     снова
    2.05
    Activations Density 0.981%

    No Known Activations